Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
MCP server for microscopes controlled by Micro-Manager (pymmcore-plus).
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
LABMCP_ADDRESS, LABMCP_SIMULATE, LABMCP_READ_ONLY, LABMCP_LIMITSYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"labmcp-micro-manager": {
"command": "uvx",
"args": [
"labmcp-micro-manager"
],
"env": {
"LABMCP_ADDRESS": "your-value",
"LABMCP_SIMULATE": "your-value",
"LABMCP_READ_ONLY": "your-value",
"LABMCP_LIMITS": "your-value"
}
}
}
}Run this in your terminal
claude mcp add labmcp-micro-manager --env LABMCP_ADDRESS=your-value --env LABMCP_SIMULATE=your-value --env LABMCP_READ_ONLY=your-value --env LABMCP_LIMITS=your-value -- uvx labmcp-micro-managerFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"labmcp-micro-manager": {
"command": "uvx",
"args": [
"labmcp-micro-manager"
],
"env": {
"LABMCP_ADDRESS": "your-value",
"LABMCP_SIMULATE": "your-value",
"LABMCP_READ_ONLY": "your-value",
"LABMCP_LIMITS": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"labmcp-micro-manager": {
"type": "stdio",
"command": "uvx",
"args": [
"labmcp-micro-manager"
],
"env": {
"LABMCP_ADDRESS": "your-value",
"LABMCP_SIMULATE": "your-value",
"LABMCP_READ_ONLY": "your-value",
"LABMCP_LIMITS": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
LABMCP_ADDRESS envLABMCP_SIMULATE envLABMCP_READ_ONLY envLABMCP_LIMITS envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account K-Dense-AI, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.3) reached the registry 42 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Tethered Trust
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Fit, compatibility and recall checks for AI agents before they buy: verdicts, evidence, receipts.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Let an AI agent snap images, acquire z-stacks and time-lapses, move the stage and focus within limits you set, switch channels and objectives, set exposure, operate shutters and run autofocus on any microscope controlled by Micro-Manager, through its open device layer (MMCore) and pymmcore-plus.
| Package | labmcp-micro-manager |
| Instruments | Any hardware with a Micro-Manager device adapter (hundreds of cameras, XY/Z stages, microscope stands, filter wheels, shutters and light sources from Hamamatsu, Photometrics, Andor, PCO, Basler, ASI, Prior, Ludl, Märzhäuser, Nikon, Zeiss, Olympus/Evident, Leica, Lumencor, CoolLED and others), described by a Micro-Manager .cfg hardware configuration |
| Interfaces | Whatever the device adapters use: USB, serial, Camera Link / CoaXPress / GigE frame grabbers |
| Protocol | Micro-Manager MMCore API via pymmcore-plus CMMCorePlus (MMCore API reference, pymmcore-plus API, configuration guide) |
| Status | 🧪 simulated: tested against a simulated microscope and against pymmcore-plus' real core with Python test devices, not yet verified on hardware. Report a hardware test |
uvx labmcp-micro-manager --simulate --check
The simulator is a widefield fluorescence microscope with a 512 x 512, 12-bit camera, an XY stage, a focus drive, a shutter, a DAPI / FITC / TRITC / Brightfield filter wheel, a 10x / 20x / 40x turret and a hardware autofocus, looking at a field of cell nuclei. Its images defocus with Z, scale with exposure, bleach with light dose, saturate at 4095 and carry shot and read noise, so focusing, exposure and bleaching behave like on a real microscope.
.cfg file with Micro-Manager's Hardware Configuration Wizard (in the Micro-Manager app), including config groups for channels (usually Channel) and objectives (Objective) and a pixel-size calibration. Close the Micro-Manager app afterwards: a device can only be opened by one program.pymmcore build. Either download them with pymmcore-plus' own installer: uvx --from labmcp-micro-manager mmcore install # into pymmcore-plus' data folder
uvx --from labmcp-micro-manager mmcore list # show what was found
or point to an existing Micro-Manager installation with `--option mm_path=/path/to/Micro-Manager` (it must be a build whose device interface matches pymmcore; `mmcore info` shows the version). Vendor camera SDKs and drivers must be installed separately, as for Micro-Manager itself.
uvx labmcp-micro-manager --address ~/scopes/Ti2_Prime95B.cfg --check
uvx labmcp-micro-manager --address MMConfig_demo.cfg --check # Micro-Manager demo devices
`--check` loads the configuration and prints the camera, stages and other device roles.
Claude Code
claude mcp add microscope -- uvx labmcp-micro-manager --address /path/to/MyScope.cfg --option z_min_um=0 --option z_max_um=4500
Claude Desktop / Cursor / Windsurf (claude_desktop_config.json, .cursor/mcp.json, …)
{
"mcpServers": { "microscope": { "command": "uvx", "args": ["labmcp-micro-manager", "--address", "/path/to/MyScope.cfg", "--option", "z_min_um=0", "--option", "z_max_um=4500", "--option", "data_dir=/data/microscope"] } } }
Add --read-only to let the agent read positions and settings without imaging or moving anything (stop_stage and close_shutter stay available). For other clients, generate the snippet with uvx labmcp config micro-manager --address /path/to/MyScope.cfg --client vscode (also cursor, codex, claude-code).
| Tool | Kind | Description |
|---|---|---|
acquire_time_lapse | ⚠️ hazard | Acquire a time-lapse at the current position: images every interval_s (optionally several channels per timepoint), saves a multi-page TIFF and reports per-frame statistics and the intensity change (bleaching). Bounded by max_frames and max_acquisition_duration_s; stop_stage aborts it. |
acquire_z_stack | ⚠️ hazard | Acquire a z-stack around the current focus: moves Z through the slices (optionally imaging several channels at each), saves a multi-page TIFF, reports per-slice statistics and the sharpest slice, and returns Z to where it started. Every slice must stay within max_z_step_um of the start and the Z soft limits. |
autofocus | ⚠️ hazard | Run the configured autofocus device (e.g. a hardware focus lock) once; it moves the focus drive. If the result is outside the Z step or soft limits, the focus is moved back and an error is raised. |
close_shutter | 🛑 safety | Close the shutter (stop illuminating the sample) and abort any running acquisition. |
get_command_log | 👁 read | Return the most recent raw commands sent to / replies received from the instrument (newest last). Useful for debugging and for recording what was done. |
get_connection_info | 👁 read | Report which instrument is connected (identity, address, simulated or real), whether the server is read-only, and the active safety limits. Call this first. |
get_exposure | 👁 read | Return the camera exposure time in milliseconds. |
get_position | 👁 read | Read the XY stage and focus (Z) positions in micrometres, and which way increasing Z moves the objective. |
get_system_info | 👁 read | Describe the microscope: loaded devices (camera, stages, shutters, filter wheels...), which device has which role, camera size/bit depth/exposure, pixel size, config groups with their presets, the current position, and the soft limits. Call this first. |
list_config_groups | 👁 read | List Micro-Manager config groups (e.g. Channel, Objective) with their presets and the preset currently active. |
move_stage_xy | ⚠️ hazard | Move the XY stage. Moves longer than max_xy_step_um or outside the XY soft limits are refused before anything moves. Make sure the objective and condenser clear the sample holder. |
move_z | ⚠️ hazard | Move the focus drive (Z). Moving the objective toward the sample can crash it into the slide: moves larger than max_z_step_um or outside the Z soft limits are refused before anything moves. |
reconnect | 🛑 safety | Close and re-open the connection to the instrument (e.g. after it was power cycled or a cable was re-plugged). |
set_config | 🎛 control | Apply a config-group preset (e.g. switch the channel: filter cube, light source, emission filter). Objective/turret groups are refused here: use set_objective. |
set_exposure | 🎛 control | Set the camera exposure time (ms). Longer exposures give brighter images but more photobleaching. Returns the exposure the camera accepted. |
set_objective | ⚠️ hazard | Switch the objective (rotates the nosepiece/turret). A longer or immersion objective can hit the sample holder or need oil/water: confirm with the user first. Pixel size changes with the objective. |
set_shutter | ⚠️ hazard | Open or close the current shutter, and optionally switch auto-shutter. An open shutter illuminates (and bleaches) the sample until it is closed again. |
snap_image | 🎛 control | Acquire one image with the current channel, exposure and position. The sample is illuminated during the exposure. Saves the full image as TIFF and returns summary statistics (min/max/mean, saturation, sharpness) plus an optional contrast-stretched preview. |
stop_stage | 🛑 safety | Immediately stop XY and Z stage motion and abort any z-stack or time-lapse in progress. |
get_connection_info, get_command_log and reconnect are built into every LabMCP server. get_command_log lists every state-changing MMCore call (setPosition(1502.0), setConfig('Channel', 'FITC'), snapImage(), ...).
| Limit | Default | Meaning |
|---|---|---|
max_z_step_um | 50 µm | Largest focus move from the current position (also the largest z-stack offset, and the largest autofocus correction accepted) |
max_xy_step_um | 20000 µm | Largest XY stage move in one call (straight-line distance) |
max_exposure_ms | 10000 ms | Longest camera exposure |
max_frames | 500 | Most images in one z-stack or time-lapse (slices or timepoints x channels) |
max_acquisition_duration_s | 3600 s | Longest time-lapse (one tool call can run at most 3600 s whatever this is set to) |
Override at launch, e.g. --limit max_z_step_um=10 --limit max_frames=2000.
Soft limits (recommended): absolute stage bounds in micrometres, set with driver options. Find them by moving to the safe extremes in Micro-Manager (e.g. Z with the objective just below the coverslip) and reading the positions:
| Option | Meaning |
|---|---|
z_min_um, z_max_um | Allowed focus range. Set the side that moves the objective toward the sample tightly. |
x_min_um, x_max_um, y_min_um, y_max_um | Allowed XY range (e.g. the area of your slide or plate holder) |
Every Z and XY move, every z-stack slice and every autofocus result is checked against the step limits and soft limits before anything moves (autofocus results are checked afterwards and undone if out of range).
get_position / get_system_info report focus_direction (whether increasing Z moves the objective toward the sample, as declared by the device adapter; often unknown). Configure z_min_um / z_max_um for every microscope you connect.set_objective) rotate the nosepiece and are marked as hazardous; set_config refuses config groups whose names look like objective or turret groups (Objective, Nosepiece, Turret, Magnification, Lens). Other groups are applied as-is: if one of your presets moves hardware near the sample, name the group accordingly or leave it out of the configuration.set_shutter(open=True) leaves the sample lit until close_shutter is called.save_path, or in --option data_dir=... (default: the system temp folder, labmcp-micro-manager/). save_path must end in .tif/.tiff and must not be a folder; it is checked before anything moves or is exposed. Existing files are never overwritten (a numeric suffix is added). Tools return statistics (min/max/mean/std, saturated fraction, a sharpness score) and a small contrast-streOnly the beginning is shown; read the rest in the repo